INDEX

Explanations

terms related to law enforcement actions

oai_token-act-pair · gpt-3.5-turbo

terms related to law enforcement activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Columb

-0.79

mers

-0.71

Brit

-0.71

bian

-0.70

wn

-0.70

iewicz

-0.69

Ã§

-0.68

gets

-0.66

aimon

-0.66

ulton

-0.65

POSITIVE LOGITS

 enforcement

1.24

 Enforcement

1.05

 crackdown

1.02

 sanction

0.95

 policies

0.87

 policy

0.86

 monitoring

0.84

 sanctions

0.84

enforcement

0.83

 infringement

0.83

Activations Density 0.013%

terms related to law enforcement actions

terms related to law enforcement activities

No Comments

No Known Activations